Correlation Assisted Strong Uncorrelating Transform Complex Common Spatial Patterns for Spatially Distant Channel Data

Abstract

The Strong Uncorrelating Transform Complex Common Spatial Patterns (SUTCCSP) algorithm, designed for multichannel data analysis, has a limitation on keeping the correlation information among channels during the simultaneous diagonalization process of the covariance and pseudocovariance matrices. This paper focuses on the importance of preserving the correlation information among multichannel data and proposes the correlation assisted SUTCCSP (CASUT) algorithm to address this issue. The performance of the proposed algorithm was demonstrated by classifying the motor imagery electroencephalogram (EEG) dataset. The features were first extracted using CSP algorithms including the proposed method, and then the random forest classifier was utilized for the classification. Experiments using CASUT yielded an average classification accuracy of 78.10 (%), which significantly outperformed those of original CSP, Complex Common Spatial Patterns (CCSP), and SUTCCSP with p-values less than 0.01, tested by the Wilcoxon signed rank test.

Youngjoo Kim

ASML, Netherlands

Her research interests include visual analytics in big data and blind signal processing with applications in astronomy and biomedicine.

Jiwoo Ryu

Embedded Software Engineer, Fugro Innovation & Technology B.V.

His research interests include image processing and biomedical signal processing.

Heejun Lee

PhD Student, University of Groningen

His research interests include biomedical signal processing and wearable IT.

Cheolsoo Park

Professor

His research interests include machine learning, adaptive signal processing, computational neuroscience, and wearable technology.